Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3815 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.8554. Min Range: -4.8554

Max Act: 4.8554. Min Act: -0.0000

Data Index: 1550065 (Python Code)

Max Activating Token Index: 901

Text #1

Max Range: 4.8554. Min Range: -4.8554

Max Act: 4.4665. Min Act: -0.0000

Data Index: 1613864 (Python Code)

Max Activating Token Index: 247

Text #2

Max Range: 4.8554. Min Range: -4.8554

Max Act: 4.2784. Min Act: -0.0000

Data Index: 1464373 (Python Code)

Max Activating Token Index: 985

Text #3

Max Range: 4.8554. Min Range: -4.8554

Max Act: 4.1546. Min Act: -0.0000

Data Index: 1511097 (Python Code)

Max Activating Token Index: 388

Text #4

Max Range: 4.8554. Min Range: -4.8554

Max Act: 3.9724. Min Act: -0.0000

Data Index: 1624109 (Python Code)

Max Activating Token Index: 882

Text #5

Max Range: 4.8554. Min Range: -4.8554

Max Act: 3.8864. Min Act: -0.0000

Data Index: 1581988 (Python Code)

Max Activating Token Index: 687

Text #6

Max Range: 4.8554. Min Range: -4.8554

Max Act: 3.9952. Min Act: -0.0000

Data Index: 1459094 (Python Code)

Max Activating Token Index: 679

Text #7

Max Range: 4.8554. Min Range: -4.8554

Max Act: 3.8525. Min Act: -0.0000

Data Index: 1601380 (Python Code)

Max Activating Token Index: 722

Text #8

Max Range: 4.8554. Min Range: -4.8554

Max Act: 4.1976. Min Act: -0.0000

Data Index: 1550688 (Python Code)

Max Activating Token Index: 789

Text #9

Max Range: 4.8554. Min Range: -4.8554

Max Act: 3.9563. Min Act: -0.0000

Data Index: 1560475 (Python Code)

Max Activating Token Index: 1013

Text #10

Max Range: 4.8554. Min Range: -4.8554

Max Act: 3.8985. Min Act: -0.0000

Data Index: 1381226 (Python Code)

Max Activating Token Index: 855

Text #11

Max Range: 4.8554. Min Range: -4.8554

Max Act: 3.8829. Min Act: -0.0000

Data Index: 1419853 (Python Code)

Max Activating Token Index: 649

Text #12

Max Range: 4.8554. Min Range: -4.8554

Max Act: 3.8500. Min Act: -0.0000

Data Index: 1585759 (Python Code)

Max Activating Token Index: 717

Text #13

Max Range: 4.8554. Min Range: -4.8554

Max Act: 3.6372. Min Act: -0.0000

Data Index: 1598663 (Python Code)

Max Activating Token Index: 667

Text #14

Max Range: 4.8554. Min Range: -4.8554

Max Act: 3.7654. Min Act: -0.0000

Data Index: 1605977 (Python Code)

Max Activating Token Index: 996

Text #15

Max Range: 4.8554. Min Range: -4.8554

Max Act: 3.6236. Min Act: -0.0000

Data Index: 1517290 (Python Code)

Max Activating Token Index: 998

Text #16

Max Range: 4.8554. Min Range: -4.8554

Max Act: 3.7911. Min Act: -0.0000

Data Index: 1496950 (Python Code)

Max Activating Token Index: 272

Text #17

Max Range: 4.8554. Min Range: -4.8554

Max Act: 3.7204. Min Act: -0.0000

Data Index: 1421414 (Python Code)

Max Activating Token Index: 297

Text #18

Max Range: 4.8554. Min Range: -4.8554

Max Act: 3.9252. Min Act: -0.0000

Data Index: 1478265 (Python Code)

Max Activating Token Index: 665

Text #19

Max Range: 4.8554. Min Range: -4.8554

Max Act: 3.7266. Min Act: -0.0000

Data Index: 1597027 (Python Code)

Max Activating Token Index: 238